← Main README · Our Survey
II. Spatial Geometry
Research on explicit human body structure, geometric recovery, and renderable avatar construction.
## Browse Categories
---
## II.1 Structured Geometry Modeling
*Explicit body, hand, and face geometry recovered from visual or multimodal evidence.*
| Method | Paper | Venue | Paper Page | Website |
|---|---|:---:|:---:|:---:|
| DirtyMoCap | DirtyMoCap: Robust Motion Capture from Unconstrained Markers | SIGGRAPH Asia 2026 | [:page_facing_up:](https://arxiv.org/abs/2609.19927 "Paper page") | [:house:](https://wanglongzju.github.io/DirtyMoCap-Project-Page/ "Homepage") [:octocat:](https://github.com/WangLongZJU/DirtyMoCap "GitHub") |
| DreamHand | DreamHand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery | arXiv 2026 | [:page_facing_up:](https://arxiv.org/abs/2608.20308 "Paper page") | [:house:](https://ggxxii.github.io/dreamhand/ "Homepage") [:octocat:](https://github.com/ggxxii/dreamhand "GitHub") |
| DETRAM | DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes | arXiv 2026 | [:page_facing_up:](https://arxiv.org/abs/2607.09089 "Paper page") | - |
| EmoteGPT | EmoteGPT: 3D Human Facial Expressions from Natural Language Descriptions | ECCV 2026 | [:page_facing_up:](https://arxiv.org/abs/2607.02674 "Paper page") | [:octocat:](https://github.com/GenIntel/EmoteGPT "GitHub") |
| Multi-HMR 2 | Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking | arXiv 2026 | [:page_facing_up:](https://arxiv.org/abs/2606.14841 "Paper page") | [:octocat:](https://github.com/naver/multi-hmr2 "GitHub") |
| DanceHMR | DanceHMR: Hand-Aware Whole-Body Human Mesh Recovery from Monocular Videos | arXiv 2026 | [:page_facing_up:](https://arxiv.org/abs/2605.18102 "Paper page") | [:house:](https://shenwenhao01.github.io/dancehmr/ "Homepage") |
| Anny-Fit | Anny-Fit: All-Age Human Mesh Recovery | CVPR 2026 Findings | [:page_facing_up:](https://arxiv.org/abs/2605.04728 "Paper page") | [:octocat:](https://github.com/naver/anny-fit "GitHub") |
| VLM-GPA | VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery | CVPR 2026 | [:page_facing_up:](https://arxiv.org/abs/2602.19180 "Paper page") | - |
| SAM 3D Body | SAM 3D Body: Robust Full-Body Human Mesh Recovery | CVPR 2026 | [:page_facing_up:](https://arxiv.org/abs/2602.15989 "Paper page") | [:octocat:](https://github.com/facebookresearch/sam-3d-body "GitHub") |
| PEAR | PEAR: Pixel-Aligned Expressive Human Mesh Recovery | SIGGRAPH 2026 | [:page_facing_up:](https://arxiv.org/abs/2601.22693 "Paper page") | [:octocat:](https://github.com/Pixel-Talk/PEAR "GitHub") |
| ContextFace | ContextFace: Generating Facial Expressions from Emotional Contexts | ICCV 2025 | [:page_facing_up:](https://openaccess.thecvf.com/content/ICCV2025/html/Kim_ContextFace_Generating_Facial_Expressions_from_Emotional_Contexts_ICCV_2025_paper.html "Paper page") | [:octocat:](https://github.com/minjung98/ContextFace_ "GitHub") |
| PromptHMR | PromptHMR: Promptable Human Mesh Recovery | CVPR 2025 | [:page_facing_up:](https://openaccess.thecvf.com/content/CVPR2025/html/Wang_PromptHMR_Promptable_Human_Mesh_Recovery_CVPR_2025_paper.html "Paper page") | [:octocat:](https://github.com/yufu-wang/PromptHMR "GitHub") |
| SMPLest-X | SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation | TPAMI 2025 | [:page_facing_up:](https://ieeexplore.ieee.org/abstract/document/11195771/ "Paper page") | [:octocat:](https://github.com/wqyin/SMPLest-X "GitHub") |
| UniPose | UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing | CVPR 2025 | [:page_facing_up:](https://openaccess.thecvf.com/content/CVPR2025/html/Li_UniPose_A_Unified_Multimodal_Framework_for_Human_Pose_Comprehension_Generation_CVPR_2025_paper.html "Paper page") | [:octocat:](https://github.com/VIPL-VISMOD/UniPose "GitHub") |
| PoseEmbroider | Poseembroider: Towards a 3d, Visual, Semantic-Aware Human Pose Representation | ECCV 2024 | [:page_facing_up:](https://arxiv.org/abs/2409.06535 "Paper page") | [:octocat:](https://github.com/naver/poseembroider "GitHub") |
| ChatPose | Chatpose: Chatting about 3d Human Pose | CVPR 2024 | [:page_facing_up:](https://openaccess.thecvf.com/content/CVPR2024/html/Feng_ChatPose_Chatting_about_3D_Human_Pose_CVPR_2024_paper.html "Paper page") | [:octocat:](https://github.com/yfeng95/PoseGPT "GitHub") |
| HaMeR | Reconstructing Hands in 3D with Transformers | CVPR 2024 | [:page_facing_up:](http://openaccess.thecvf.com/content/CVPR2024/html/Pavlakos_Reconstructing_Hands_in_3D_with_Transformers_CVPR_2024_paper.html "Paper page") | [:octocat:](https://github.com/geopavlakos/hamer "GitHub") |
| SMPLer-X | SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation | NeurIPS 2023 | [:page_facing_up:](https://proceedings.neurips.cc/paper_files/paper/2023/hash/2614947a25d7c435bcd56c51958ddcb1-Abstract-Datasets_and_Benchmarks.html "Paper page") | [:octocat:](https://github.com/caizhongang/SMPLer-X "GitHub") |
Back to top ↑
---
## II.2 Renderable Avatar Modeling
*Renderable and animatable human assets reconstructed or generated from limited observations.*
| Method | Paper | Venue | Paper Page | Website |
|---|---|:---:|:---:|:---:|
| 4DAnyone | 4DAnyone: Create Anyone in 4D from a Casual Monocular Video | SIGGRAPH Asia 2026 | [:page_facing_up:](https://arxiv.org/abs/2608.20335 "Paper page") | [:house:](https://4danyone.github.io/ "Homepage") [:octocat:](https://github.com/ant-research/4DAnyone "GitHub") [🤗](https://huggingface.co/AntResearch/4DAnyone "Hugging Face") |
| FlexiAvatar | FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility | ECCV 2026 | [:page_facing_up:](https://arxiv.org/abs/2607.19100 "Paper page") | [:house:](https://yihalem1.github.io/FlexiAvatar/ "Homepage") |
| DreamCharacter-1 | DreamCharacter-1: From 3D Generative Foundation Models to Product-Ready Character Generation | arXiv 2026 | [:page_facing_up:](https://arxiv.org/abs/2607.07817 "Paper page") | [:house:](https://dreamcharacter-x.github.io/ "Homepage") |
| FiCA | FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Image | arXiv 2026 | [:page_facing_up:](https://arxiv.org/abs/2606.24232 "Paper page") | [:house:](https://kim-youwang.github.io/FiCA "Homepage") |
| HumanNOVA | HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image | CVPR 2026 | [:page_facing_up:](https://arxiv.org/abs/2606.02573 "Paper page") | [:octocat:](https://github.com/HumanNOVA/HumanNOVA "GitHub") |
| HeadsUp | Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures | ECCV 2026 | [:page_facing_up:](https://arxiv.org/abs/2605.04035 "Paper page") | [:house:](https://apple.github.io/ml-headsup/ "Homepage") |
| Face Anything | Face Anything: 4D Face Reconstruction from Any Image Sequence | ECCV 2026 | [:page_facing_up:](https://arxiv.org/abs/2604.19702 "Paper page") | [:house:](https://kocasariumut.github.io/FaceAnything/ "Homepage") |
| GenLCA | GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos | ECCV 2026 | [:page_facing_up:](https://arxiv.org/abs/2604.07273 "Paper page") | [:house:](https://onethousandwu.com/GenLCA-Page/ "Homepage") |
| LCA | Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining | CVPR 2026 | [:page_facing_up:](https://arxiv.org/abs/2604.02320 "Paper page") | [:house:](https://junxuan-li.github.io/lca/ "Homepage") |
| Portrait 3D Presence | Bringing Your Portrait to 3D Presence | CVPR 2026 | [:page_facing_up:](https://openaccess.thecvf.com/content/CVPR2026/html/Zhang_Bringing_Your_Portrait_to_3D_Presence_CVPR_2026_paper.html "Paper page") | - |
| InfiniHuman | InfiniHuman: Realistic 3D Human Creation with Precise Control | SIGGRAPH Asia 2025 | [:page_facing_up:](https://arxiv.org/abs/2510.11650 "Paper page") | [:house:](https://yuxuan-xue.com/infini-human "Homepage") |
| MV-Performer | MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis | SIGGRAPH Asia 2025 | [:page_facing_up:](https://arxiv.org/abs/2510.07190 "Paper page") | [:octocat:](https://github.com/zyhbili/MV-Performer "GitHub") |
| SIGMAN | SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets | ICCV 2025 | [:page_facing_up:](https://arxiv.org/abs/2504.06982 "Paper page") | [:house:](https://yyvhang.github.io/SIGMAN_3D/ "Homepage") |
| LHM | LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds | ICCV 2025 | [:page_facing_up:](https://arxiv.org/abs/2503.10625 "Paper page") | [:octocat:](https://github.com/aigc3d/LHM "GitHub") |
| AniGS | AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction | CVPR 2025 | [:page_facing_up:](https://openaccess.thecvf.com/content/CVPR2025/html/Qiu_AniGS_Animatable_Gaussian_Avatar_from_a_Single_Image_with_Inconsistent_CVPR_2025_paper.html "Paper page") | [:octocat:](https://github.com/aigc3d/AniGS "GitHub") |
| Avat3r | Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars | ICCV 2025 | [:page_facing_up:](https://openaccess.thecvf.com/content/ICCV2025/html/Kirschstein_Avat3r_Large_Animatable_Gaussian_Reconstruction_Model_for_High-fidelity_3D_Head_ICCV_2025_paper.html "Paper page") | [:house:](https://tobias-kirschstein.github.io/avat3r/ "Homepage") |
| HuGe100K | IDOL: Instant Photorealistic 3D Human Creation from a Single Image | CVPR 2025 | [:page_facing_up:](https://openaccess.thecvf.com/content/CVPR2025/html/Zhuang_IDOL_Instant_Photorealistic_3D_Human_Creation_from_a_Single_Image_CVPR_2025_paper.html "Paper page") | [:octocat:](https://github.com/yiyuzhuang/IDOL "GitHub") |
| LUCAS | LUCAS: Layered Universal Codec Avatars | CVPR 2025 | [:page_facing_up:](http://openaccess.thecvf.com/content/CVPR2025/html/Liu_LUCAS_Layered_Universal_Codec_Avatars_CVPR_2025_paper.html "Paper page") | - |
| Pippo | Pippo: High-Resolution Multi-View Humans from a Single Image | CVPR 2025 | [:page_facing_up:](https://openaccess.thecvf.com/content/CVPR2025/html/Kant_Pippo_High-Resolution_Multi-View_Humans_from_a_Single_Image_CVPR_2025_paper.html "Paper page") | [:octocat:](https://github.com/facebookresearch/pippo "GitHub") |
Back to top ↑
---
← Visual Appearance · All Survey Resources · Kinematic Dynamics →